Advertisement

Automatic classification of dialog acts with Semantic Classification Trees and Polygrams

  • Marion Mast
  • Heinrich Niemann
  • Elmar Nöth
  • Ernst Günter Schukat-Talamazzini
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1040)

Abstract

This paper presents automatic methods for the classification of dialog acts. In the verbmobil application (speech-to-speech translation of face-to-face dialogs) maximally 50 % of the utterances are analyzed in depth and for the rest, shallow processing takes place. The dialog component keeps track of the dialog with this shallow processing. For the classification of utterances without in depth processing two methods are presented: Semantic Classification Trees and Polygrams. For both methods the classification algorithm is trained automatically from a corpus of labeled data. The novel idea with respect to SCTs is the use of dialog state dependent CTs and with respect to Polygrams it is the use of competing language models for the classification of dialog acts.

Keywords

automatic learning dialog act classification hidden polygram models polygrams semantic classification trees 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [AMR95]
    J. Alexandersson, E. Maier, and N. Reithinger. A robust and efficient three-layered dialogue component for a speech-to-speech translation system. In EACL 1995, to appear 1995.Google Scholar
  2. [Fis94]
    J. Fischer. Integrierte Erkennung von Phrasengrenzen und Phrasenakzenten mit Klassifikationsbäumen. Diplomarbeit, Lehrstuhl für Mustererkennung (Informatik 5), Universität Erlangen-Nürnberg, 1994.Google Scholar
  3. [GRD91]
    S. Gelfand, C. Ravishankar, and E. Delp. An Iterative Growing and Pruning Algorithm for Classification Tree Design. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13:302–320, Februar 1991.Google Scholar
  4. [Jel90]
    F. Jelinek. Self-Organized Language Modeling for Speech Recognition. In A. Waibel and K.F. Lee, editors, Readings in Speech Recognition, pages 450–506. Morgan Kaufmann, San Mateo, CA, 1990.Google Scholar
  5. [JM80]
    F. Jelinek and R.L. Mercer. Interpolated Estimation of Markov Source Parameters from Sparse Data. In E.S. Gelsema and L.N. Kanal, editors, Pattern Recognition in Practice, pages 381–397. North Holland, 1980.Google Scholar
  6. [Kat87]
    S. Katz. Estimation of Probability from Sparse Data for the Language Model Component at a Speech Recognizer. IEEE Trans. on Acoustics, Speech and Signal Processing, ASSP-35(3):400–401, 1987.Google Scholar
  7. [KM93]
    S. Kameyama and I. Maleck. Konstellation und Szenario von Terminabsprachen, Verbmobil-Report-23-93, Dezember 1993.Google Scholar
  8. [KNST94]
    T. Kuhn, H. Niemann, and E.G. Schukat-Talamazzini. Ergodic Hidden Markov Models and Polygrams for Language Modeling. In Proc. Int. Conf. on Acoustics, Speech and Signal Processing, volume 1, pages 357–360, Adelaide, Australia, 1994.Google Scholar
  9. [Kuh92]
    R. Kuhn. Keyword Classification Trees for Speech Understanding Systems. Technical report, CRIM, Montreal, Canada, 1992.Google Scholar
  10. [Mai94]
    E. Maier, editor. Dialogmodellierung in VERBMOBIL — Festlegung der Sprechhandlungen für den Demonstrator Verbmobil-Memo-31-94. Juli 1994.Google Scholar
  11. [Rab88]
    L.R. Rabiner. Mathematical Foundations of Hidden Markov Models. In H. Niemann, M. Lang, and G. Sagerer, editors, Recent Advances in Speech Understanding and Dialog Systems, volume 46 of NATO ASI Series F, pages 183–205. Springer-Verlag, Berlin, 1988.Google Scholar
  12. [STHKN95]
    E.G. Schukat-Talamazzini, R. Hendrych, R. Kompe, and H. Niemann. Permugram language models. In Proc. European Conf. on Speech Communication and Technology, volume 3, pages 1773–1776, Madrid, September 1995.Google Scholar
  13. [STKN94]
    E.G. Schukat-Talamazzini, T. Kuhn, and H. Niemann. Speech Recognition for Spoken Dialogue Systems. In Niemann, de Mori, and Hanrieder, editors, Progress and Prospects of Speech Research and Technology: Proc. of the CRIM/FORWISS Workshop (München, Sept. 1994), pages 110–120, Sankt Augustin, 1994. infix.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Marion Mast
    • 1
  • Heinrich Niemann
    • 1
  • Elmar Nöth
    • 1
  • Ernst Günter Schukat-Talamazzini
    • 1
  1. 1.Lehrstuhl für MustererkennungUniversität Erlangen-NürnbergErlangen

Personalised recommendations